Abstract
We propose a novel Expanded Parts based Metric Learning (EPML) model for face verification. The model is capable of mining out the discriminative regions at the right locations and scales, for identity based matching of face images. It performs well in the presence of occlusions, by avoiding the occluded regions and selecting the next best visible regions. We show quantitatively, by experiments on the standard benchmark dataset Labeled Faces in the Wild (LFW), that the model works much better than the traditional method of face representation with metric learning, both (i) in the presence of heavy random occlusions and, (ii) also, in the case of focussed occlusions of discriminative face regions such as eyes or mouth. Further, we present qualitative results which demonstrate that the method is capable of ignoring the occluded regions while exploiting the visible ones.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Mignon, A., Jurie, F.: PCCA: a new approach for distance learning from sparse pairwise constraints. In: CVPR (2012)
Simonyan, K., Parkhi, O.M., Vedaldi, A., Zisserman, A.: Fisher vector faces in the wild. In: BMVC (2013)
Guillaumin, M., Verbeek, J., Schmid, C.: Is that you? Metric learning approaches for face identification. In: ICCV (2009)
Chen, D., Cao, X., Wen, F., Sun, J.: Blessing of dimensionality: high-dimensional feature and its efficient compression for face verification. In: CVPR (2013)
Leonardis, A., Bischof, H.: Dealing with occlusions in the eigenspace approach. In: CVPR (1996)
Simonyan, K., Vedaldi, A., Zisserman, A.: Deep fisher networks for large-scale image classification. In: NIPS (2013)
Taigman, Y., Yang, M., Ranzato, M., Wolf, L.: Deepface: closing the gap to human-level performance in face verification. In: CVPR (2014)
Rama, A., Tarres, F., Goldmann, L., Sikora, T.: More robust face recognition by considering occlusion information. In: FG (2008)
Colombo, A., Cusano, C., Schettini, R.: Detection and restoration of occlusions for 3d face recognition. In: ICME (2006)
Colombo, A., Cusano, C., Schettini, R.: Recognizing faces in 3d images even in presence of occlusions. In: BTAS (2008)
Everson, R., Sirovich, L.: Karhunen-loeve procedure for gappy data. JOSA A 12, 1657–1664 (1995)
Lin, D., Tang, X.: Quality-driven face occlusion detection and recovery. In: CVPR (2007)
Oh, H.J., Lee, K.M., Lee, S.U.: Occlusion invariant face recognition using selective local non-negative matrix factorization basis images. IVC 26, 1515–1523 (2008)
Wright, J., Yang, A.Y., Ganesh, A., Sastry, S.S., Ma, Y.: Robust face recognition via sparse representation. PAMI 31, 210–227 (2009)
Zhou, Z., Wagner, A., Mobahi, H., Wright, J., Ma, Y.: Face recognition with contiguous occlusion using markov random fields. In: CVPR (2009)
Ou, W., You, X., Tao, D., Zhang, P., Tang, Y., Zhu, Z.: Robust face recognition via occlusion dictionary learning. PR 47, 1559–1572 (2014)
Andrés, A.M., Padovani, S., Tepper, M., Jacobo-Berlles, J.: Face recognition on partially occluded images using compressed sensing. PRL 36, 235–242 (2014)
Min, R., Hadid, A., Dugelay, J.: Improving the recognition of faces occluded by facial accessories. In: FG (2011)
Ojala, T., Pietikainen, M., Maenpaa, T.: Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. PAMI 24, 971–987 (2002)
Tajima, Y., Ito, K., Aoki, T., Hosoi, T., Nagashima, S., Kobayashi, K.: Performance improvement of face recognition algorithms using occluded-region detection. In: ICB (2013)
Alyuz, N., Gokberk, B., Akarun, L.: 3-d face recognition under occlusion using masked projection. IEEE Trans. Inf. Forensics and Secur. 8, 789–802 (2013)
Min, R., Hadid, A., Dugelay, J.L.L.: Efficient detection of occlusion prior to robust face recognition. Sci. World J. 2014, 10 (2014). 519158
Colombo, A., Cusano, C., Schettini, R.: Three-dimensional occlusion detection and restoration of partially occluded faces. J. Math. Imaging Vis. 40, 105–119 (2011)
Liao, S., Jain, A.K., Li, S.Z.: Partial face recognition: alignment-free approach. PAMI 35, 1193–1205 (2013)
Weng, R., Lu, J., Hu, J., Yang, G., Tan, Y.P.P.: Robust feature set matching for partial face recognition. In: ICCV (2013)
Zhao, X., He, Z., Zhang, S., Kaneko, S., Satoh, Y.: Robust face recognition using the GAP feature. PR 46, 2647–2657 (2013)
Huang, G.B., Ramesh, M., Berg, T., Learned-Miller, E.: Labeled faces in the wild: a database for studying face recognition in unconstrained environments. Technical report 07–49, University of Massachusetts, Amherst (2007)
Berg, T., Belhumeur, P.N.: POOF: part-based one-vs.-one features for fine-grained categorization, face verification, and attribute estimation. In: CVPR (2013)
Li, H., Hua, G., Lin, Z., Brandt, J., Yang, J.: Probabilistic elastic matching for pose variant face verification. In: CVPR (2013)
Cao, Q., Ying, Y., Li, P.: Similarity metric learning for face recognition. In: ICCV (2013)
Cui, Z., Li, W., Xu, D., Shan, S., Chen, X.: Fusing robust face region descriptors via multiple metric learning for face recognition in the wild. In: CVPR (2013)
Sun, Y., Wang, X., Tang, X.: Hybrid deep learning for face verification. In: ICCV (2013)
Barkan, O., Weill, J., Wolf, L., Aronowitz, H.: Fast high dimensional vector multiplication face recognition. In: ICCV (2013)
Wolf, L., Hassner, T., Taigman, Y.: Similarity scores based on background samples. In: Zha, H., Taniguchi, R., Maybank, S. (eds.) ACCV 2009, Part II. LNCS, vol. 5995, pp. 88–97. Springer, Heidelberg (2010)
Nguyen, H.V., Bai, L.: Cosine similarity metric learning for face verification. In: Kimmel, R., Klette, R., Sugimoto, A. (eds.) ACCV 2010, Part II. LNCS, vol. 6493, pp. 709–720. Springer, Heidelberg (2011)
Kumar, N., Berg, A.C., Belhumeur, P.N., Nayar, S.K.: Attribute and simile classifiers for face verification. In: ICCV (2009)
Berg, T., Belhumeur, P.N.: Tom-vs-pete classifiers and identity-preserving alignment for face verification. In: BMVC (2012)
Viola, P., Jones, M.J.: Robust real-time face detection. Intl. J. Comput. Vis. 57, 137–154 (2004)
Doersch, C., Gupta, A., Efros, A.A.: Mid-level visual element discovery as discriminative mode seeking. In: NIPS (2013)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR (2006)
Sharma, G., Jurie, F.: Learning discriminative representation image classification. In: BMVC (2011)
Jiang, L., Tong, W., Meng, D., Hauptmann, A.G.: Towards efficient learning of optimal spatial bag-of-words representations. In: ICMR (2014)
Sharma, G., Jurie, F., Schmid, C.: Expanded parts model for human attribute and action recognition in still images. In: CVPR (2013)
Vedaldi, A., Fulkerson, B.: VLFeat: an open and portable library of computer vision algorithms (2008). http://www.vlfeat.org/
Acknowledgement
This work was partially supported by the FP7 European integrated project AXES and by the ANR project PHYSIONOMIE.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Sharma, G., Jurie, F., Pérez, P. (2015). EPML: Expanded Parts Based Metric Learning for Occlusion Robust Face Verification. In: Cremers, D., Reid, I., Saito, H., Yang, MH. (eds) Computer Vision -- ACCV 2014. ACCV 2014. Lecture Notes in Computer Science(), vol 9006. Springer, Cham. https://doi.org/10.1007/978-3-319-16817-3_4
Download citation
DOI: https://doi.org/10.1007/978-3-319-16817-3_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16816-6
Online ISBN: 978-3-319-16817-3
eBook Packages: Computer ScienceComputer Science (R0)